Deep Reinforcement Learning: A Survey

Deep reinforcement learning (DRL) integrates the feature representation ability of deep learning with the decision-making ability of reinforcement learning so that it can achieve powerful end-to-end learning control capabilities. In the past decade, DRL has made substantial advances in many tasks that require perceiving high-dimensional input and making optimal or near-optimal decisions. However, there are still many challenging problems in the theory and applications of DRL, especially in learning control tasks with limited samples, sparse rewards, and multiple agents. Researchers have proposed various solutions and new theories to solve these problems and promote the development of DRL. In addition, deep learning has stimulated the further development of many subfields of reinforcement learning, such as hierarchical reinforcement learning (HRL), multiagent reinforcement learning, and imitation learning. This article gives a comprehensive overview of the fundamental theories, key algorithms, and primary research domains of DRL. In addition to value-based and policy-based DRL algorithms, the advances in maximum entropy-based DRL are summarized. The future research topics of DRL are also analyzed and discussed.

Automated summary

Deep reinforcement learning (DRL) is a technology that combines deep learning with reinforcement learning, achieving significant progress in tasks that involve perceiving high-dimensional input and making optimal decisions. However, there are still challenges in both theory and applications, especially in scenarios with limited samples, sparse rewards, and multiple agents. Researchers have proposed solutions and new theories to advance DRL and stimulate the development of subfields in reinforcement learning.